Running Agent Workflows with Nemotron 3 Ultra
NVIDIAAI · x · 2026-07-17
NVIDIA shared a new video demonstrating how to run **NVIDIA Nemotron 3 Ultra** using **Baseten + Deep Agents Code**. Key highlights from the video include: - **550B parameters**, with speeds up to roughly **300 tokens/s** - Endpoint Agent capabilities supporting **skills**, **sub-agents**, and **MCP** - First-class tracing via **LangSmith** Overall, this serves as a practical engineering demonstration of an agent workflow rather than just a standard model showcase.
Related event: LangChain Demonstrates Nemotron 3 Ultra Agent Workflow(4 posts)→
More from coding & agent
- Autoresearch proposes packaging ML runs as studies with questions, analysis, and code diffs — morgymcg · 2026-07-21
- CHAP defines approvals, handoffs, and audit logs for human-agent workflows — DeliveryTechnical199 · 2026-07-21
- The author says Codex reached 20x and is now debugging spec decoding on a hybrid parallel setup — TheZachMueller · 2026-07-21
- Axcess adds an MCP connector for WCAG accessibility checks that scanners miss — modelcontextprotocol · 2026-07-21
- X post asks whether Cursor Composer, built on Kimi models, would also be banned — max_paperclips · 2026-07-21
- A developer’s Codex usage is draining pooled enterprise credits at a small company — Distinct_Relation_62 · 2026-07-21